What are the hardware requirements for Sheared LLaMA 2.7B Pruned?

Sheared LLaMA 2.7B Pruned requires approximately 5.4 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Sheared LLaMA 2.7B Pruned and how large is it?

Sheared LLaMA 2.7B Pruned is developed by princeton-nlp, a model with 2.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Sheared LLaMA 2.7B Pruned?

Sheared LLaMA 2.7B Pruned is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Sheared LLaMA 2.7B Pruned by princeton-nlp — VRAM 5.4GB, 4K context

Name: Sheared LLaMA 2.7B Pruned
Author: princeton-nlp

Sheared LLaMA 2.7B Pruned is an open-source language model by princeton-nlp. Features: 2.7b LLM, VRAM: 5.4GB, Context: 4K, License: llama2, LLM Explorer Score: 0.1.

Arxiv:2310.06694 Endpoints compatible Llama Pytorch Region:us

Model Card on HF 🤗: https://huggingface.co/princeton-nlp/Sheared-LLaMA-2.7B-Pruned

Sheared LLaMA 2.7B Pruned Parameters and Internals

Model Type

Pruned Model

Use Cases

Areas:

Research

Applications:

Study effective data mixtures for continued pre-training, Comparisons to other pruning techniques, Understand how pruning affects knowledge and reasoning capabilities

Additional Notes

Sheared-LLaMA-2.7B-Pruned is based on 'meta-llama/Llama-2-7b-hf' without continued pre-training.

Training Details

Data Sources:

Roughly 0.4B tokens

Data Volume:

0.4B tokens

Methodology:

Pruning experiment without continued pre-training

LLM Name	Sheared LLaMA 2.7B Pruned
Repository 🤗	https://huggingface.co/princeton-nlp/Sheared-LLaMA-2.7B-Pruned
Model Size	2.7b
Required VRAM	5.4 GB
Updated	2026-07-31
Maintainer	princeton-nlp
Model Type	llama
Model Files	5.4 GB
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.33.0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Sheared LLaMA 2.7B Pruned capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Sheared LLaMA 2.7B Pruned

Best Alternatives	Context / RAM	Downloads	Likes
Sheared LLaMA 2.7B	4K / 10.8 GB	821	61
Dopeyshearedplats 2.7B V1	4K / 5.7 GB	214	2
...redplats 2.7B V2 Instruct V0.1	4K / 5.4 GB	5	3
Shearedplats 2.7B V2	4K / 5.7 GB	226	2
Llama Final	4K / 5.5 GB	5	0
DPO VinaLlama Completed	4K / 5.6 GB	8	0
Urllm Ko En 2.7B	4K / 11.2 GB	5	0
...heared Llama 2.7B Deita 6K Sft	4K / 5.4 GB	4	1
Sheared LLaMA 2.7B Weblinx	4K / 5.4 GB	23	2
Vinallama 2.7B Chat	4K / 5.5 GB	370	16

Note: green Score (e.g. "73.2") means that the model is better than princeton-nlp/Sheared-LLaMA-2.7B-Pruned.